Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    包含
    -0.07
     бед
    -0.07
     Redistributions
    -0.06
    ビー
    -0.06
    困
    -0.06
     Edwin
    -0.06
    ้าของ
    -0.06
    onda
    -0.06
     مرح
    -0.06
     щ
    -0.06
    POSITIVE LOGITS
     sub
    0.11
     Sub
    0.09
    --)
↵
    0.07
     determ
    0.07
    SubMenu
    0.07
     vm
    0.06
    (predicate
    0.06
    cca
    0.06
     vampire
    0.06
    _ttl
    0.06
    Act Density 0.010%

    No Known Activations